Contact Wasserstein Geodesics for Non-Conservative Schrödinger Bridges

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Testa, Andrea, Hauberg, Søren, Asfour, Tamim, Rozo, Leonel
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913097813327872
author Testa, Andrea
Hauberg, Søren
Asfour, Tamim
Rozo, Leonel
author_facet Testa, Andrea
Hauberg, Søren
Asfour, Tamim
Rozo, Leonel
contents The Schrödinger Bridge provides a principled framework for modeling stochastic processes between distributions; however, existing methods are limited by energy-conservation assumptions, which constrains the bridge's shape preventing it from model varying-energy phenomena. To overcome this, we introduce the non-conservative generalized Schrödinger bridge (NCGSB), a novel, energy-varying reformulation based on contact Hamiltonian mechanics. By allowing energy to change over time, the NCGSB provides a broader class of real-world stochastic processes, capturing richer and more faithful intermediate dynamics. By parameterizing the Wasserstein manifold, we lift the bridge problem to a tractable geodesic computation in a finite-dimensional space. Unlike computationally expensive iterative solutions, our contact Wasserstein geodesic (CWG) is naturally implemented via a ResNet architecture and relies on a non-iterative solver with near-linear complexity. Furthermore, CWG supports guided generation by modulating a task-specific distance metric. We validate our framework on tasks including manifold navigation, molecular dynamics predictions, and image generation, demonstrating its practical benefits and versatility.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06856
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Contact Wasserstein Geodesics for Non-Conservative Schrödinger Bridges
Testa, Andrea
Hauberg, Søren
Asfour, Tamim
Rozo, Leonel
Machine Learning
Differential Geometry
37K25 (Primary) 53D25, 49Q22 (Secondary)
The Schrödinger Bridge provides a principled framework for modeling stochastic processes between distributions; however, existing methods are limited by energy-conservation assumptions, which constrains the bridge's shape preventing it from model varying-energy phenomena. To overcome this, we introduce the non-conservative generalized Schrödinger bridge (NCGSB), a novel, energy-varying reformulation based on contact Hamiltonian mechanics. By allowing energy to change over time, the NCGSB provides a broader class of real-world stochastic processes, capturing richer and more faithful intermediate dynamics. By parameterizing the Wasserstein manifold, we lift the bridge problem to a tractable geodesic computation in a finite-dimensional space. Unlike computationally expensive iterative solutions, our contact Wasserstein geodesic (CWG) is naturally implemented via a ResNet architecture and relies on a non-iterative solver with near-linear complexity. Furthermore, CWG supports guided generation by modulating a task-specific distance metric. We validate our framework on tasks including manifold navigation, molecular dynamics predictions, and image generation, demonstrating its practical benefits and versatility.
title Contact Wasserstein Geodesics for Non-Conservative Schrödinger Bridges
topic Machine Learning
Differential Geometry
37K25 (Primary) 53D25, 49Q22 (Secondary)
url https://arxiv.org/abs/2511.06856